End of training

README.md

@@ -0,0 +1,80 @@
+---
+library_name: transformers
+base_model: huawei-noah/TinyBERT_General_4L_312D
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: FP16-KD-NID
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# FP16-KD-NID
+
+This model is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0424
+- Accuracy: 0.9919
+- Precision: 0.9348
+- Recall: 0.9215
+- F1 score: 0.9238
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 650
+- eval_batch_size: 650
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1 score |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:--------:|
+| 0.1582        | 1.0   | 1828  | 0.1329          | 0.9827   | 0.8730    | 0.8321 | 0.8307   |
+| 0.1112        | 2.0   | 3656  | 0.1033          | 0.9853   | 0.8697    | 0.8584 | 0.8529   |
+| 0.0927        | 3.0   | 5484  | 0.0820          | 0.9879   | 0.9209    | 0.8790 | 0.8789   |
+| 0.0828        | 4.0   | 7312  | 0.0689          | 0.9893   | 0.9233    | 0.8953 | 0.8980   |
+| 0.0711        | 5.0   | 9140  | 0.0637          | 0.9898   | 0.9204    | 0.9024 | 0.9017   |
+| 0.0673        | 6.0   | 10968 | 0.0595          | 0.9901   | 0.9206    | 0.9080 | 0.9051   |
+| 0.0514        | 7.0   | 12796 | 0.0538          | 0.9907   | 0.9273    | 0.9084 | 0.9100   |
+| 0.0522        | 8.0   | 14624 | 0.0518          | 0.9909   | 0.9266    | 0.9103 | 0.9123   |
+| 0.0478        | 9.0   | 16452 | 0.0492          | 0.9911   | 0.9352    | 0.9105 | 0.9148   |
+| 0.0478        | 10.0  | 18280 | 0.0463          | 0.9914   | 0.9335    | 0.9153 | 0.9185   |
+| 0.0415        | 11.0  | 20108 | 0.0461          | 0.9914   | 0.9282    | 0.9171 | 0.9169   |
+| 0.0394        | 12.0  | 21936 | 0.0445          | 0.9916   | 0.9328    | 0.9190 | 0.9204   |
+| 0.0377        | 13.0  | 23764 | 0.0435          | 0.9917   | 0.9358    | 0.9180 | 0.9217   |
+| 0.0342        | 14.0  | 25592 | 0.0429          | 0.9918   | 0.9346    | 0.9190 | 0.9214   |
+| 0.0383        | 15.0  | 27420 | 0.0424          | 0.9919   | 0.9348    | 0.9215 | 0.9238   |
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,84 @@
+{
+  "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "dim": 312,
+  "dropout": 0.1,
+  "emb_size": 312,
+  "hidden_act": "gelu",
+  "hidden_dim": 3072,
+  "hidden_dropout_prob": 0.1,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1200,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 4,
+  "pad_token_id": 0,
+  "pre_trained": "",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "structure": [],
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8816b873ed942c76eb8d896ef6715d5c0eab82b9df1fe289cba6dda99c03d20a
+size 76157040

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9be1820c2e6b0a18384c6701c68bdc322a256f474d2595771f2c74cdfd78e7
+size 5304